Tree-Based Codification in Neural Architecture Search for Medical Image Segmentation
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @Article{Fuentes-Tomas:TEVC,
-
author = "Jose-Antonio Fuentes-Tomas and Efren Mezura-Montes and
Hector-Gabriel Acosta-Mesa and Aldo Marquez-Grajales",
-
journal = "IEEE Transactions on Evolutionary Computation",
-
title = "Tree-Based Codification in Neural Architecture Search
for Medical Image Segmentation",
-
note = "Early access",
-
abstract = "Convolutional Neural Networks (CNNs) have shown a
competitive performance in medical imaging
applications, such as image segmentation. However,
choosing an existing architecture capable of adapting
to a specific dataset is challenging and requires
design expertise. Neural Architecture Search (NAS) is
employed to overcome these limitations. NAS uses
techniques to design the Neural Networks architecture.
Typically, the models' weights optimisation is carried
out using a continuous loss function, unlike model
topology optimisation, which is highly influenced by
the specific problem. Genetic Programming (GP) is an
Evolutionary Algorithm (EA) capable of adapting to the
topology optimisation problem of CNNs by considering
the attributes of its representation. A tree
representation can express complex connectivity and
apply variation operations. This paper presents a
tree-based GP algorithm for evolving CNNs based on the
well-known U-Net architecture producing compact and
flexible models for medical image segmentation across
multiple domains. This proposal is called Neural
Architecture Search / Genetic Programming / U-Net
(NASGP-Net). NASGP-Net uses a cell-based encoding and
U-Net architecture as a backbone to construct CNNs
based on a hierarchical arrangement of primitive
operations. Our experiments indicate that our approach
can produce remarkable segmentation results with fewer
parameters regarding fixed architectures. Moreover,
NASGP-Net presents competitive results against NAS
methods. Finally, we observed notable performance
improvements based on several evaluation metrics,
including Dice similarity coefficient (DSC),
Intersection over union (IoU), and Hausdorff Distance
(HD).",
-
keywords = "genetic algorithms, genetic programming, Image
segmentation, Computer architecture, Biomedical
imaging, Statistics, Sociology, Convolution,
Syntactics, Neural Architecture Search, ANN,
Convolutional Neural Networks, Medical Image
Segmentation",
-
DOI = "doi:10.1109/TEVC.2024.3353182",
-
ISSN = "1941-0026",
-
notes = "Also known as \cite{10391062}",
- }
Genetic Programming entries for
Jose-Antonio Fuentes-Tomas
Efren Mezura-Montes
Hector-Gabriel Acosta-Mesa
Aldo Marquez-Grajales
Citations